I need dataset(s) (with source link(s)) in order to determine the current state

I need dataset(s) (with source link(s)) in order to determine the current state of the Diagnosis Gaps caused by the delaying health screenings and routine medical check-ups because of COVID-19. I need the data to be Time series one at least over the last 2 years, or two ‘of the same’ dataset one pre-Covid and one post-Covid in order to answer the this question. I also need a simple machine learning model that predicts the narrowing of these gaps.
Let me say it again clearer: During the initial months of Covid-19 pandemic and associated lockdowns, regular health and diagnosis screenings were delayed. While minor checkups such as dental might not cause major health concerns to healthy individuals, other important once such as annual screenings for breast cancer may now present an advanced state case of the disease. This have caused diagnosis gaps to emerge. MY GOAL is to establish pre-covid baselines utilizing claims data in order understand the current state of the screenings and diagnosis gaps. . I also want to build a scalable model that predicts the narrowing of these gaps.
To put what I am asking in one sentence: The goal of this project is to establish pre-covid baselines in order to understand the current states of the screenings and diagnosis gaps and to predict the narrowing of these gaps using machine learning.
I want it to be as simple as possible, and as straight forward as possible. I am thinking of using the averages pre-covid and the averages post-covid to determine the current state of the diagnosis gaps caused by the pandemic.
I need the Jupyter Notebook to be clearly stating what is and why you determine to use each block of code using Jupyter Notebook markdown so I understand what is going on.